© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82634
    Prev
    Next
    INDEX
    Explanations

    ball or balls

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects tokens that are part of LaTeX-style mathematical notation (e.g. backslashes, braces, subscripts/superscripts, and math symbols).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tourisme
    -0.81
    搐
    -0.75
     зоны
    -0.75
     Pary
    -0.72
    space
    -0.72
    꽃
    -0.69
     chaises
    -0.68
     يكون
    -0.68
    реи
    -0.68
    GND
    -0.68
    POSITIVE LOGITS
     ball
    2.11
     balls
    1.88
     Balls
    1.63
     Ball
    1.63
    Ball
    1.62
    球
    1.56
    BALL
    1.53
     BALL
    1.52
    ball
    1.48
     discs
    1.42
    Activations Density 0.029%

    No Known Activations